OCR-Based Learning Recommendation System for Formula Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional learning services lack the ability to assist learners in finding specific learning topics they want to learn, limiting the learning experience to sequential presentation based on a predefined curriculum.

Innovation Solution

A learning recommendation apparatus and method that uses character recognition to detect formulas from images, allowing learners to photograph problems, and then recommends related learning topics based on concept distance from the learner's history, prioritizing recommendations for easier learning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If learning topics are presented sequentially according to a predefined curriculum, then the learning structure is organized and complete, but learners cannot easily find specific learning topics they want to learn selectively

Engineering Contradiction:

Improveselective learning capabilityVSAvoidlearning service complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system enables learners to independently initiate topic searches by photographing problems, with the system automatically recognizing the problem and recommending relevant learning topics without requiring learners to navigate through the entire curriculum structure manually

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual navigation mechanism (learners flipping through curriculum pages) with an optical recognition system (camera + OCR) that automatically identifies problems and retrieves relevant learning topics from the database

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If learners manually search through learning topics to find what they want to learn, then they can find specific topics, but it consumes significant time and effort

Engineering Contradiction:

Improvetopic search easeVSAvoidtime to find learning topic

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system pre-organizes learning topics in a database with problem-topic associations established in advance, allowing instant retrieval when a problem is photographed, eliminating the need for learners to search through topics sequentially

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary system (camera + OCR + recommendation engine) between the learner and the learning topics, which automatically translates a photographed problem into relevant topic recommendations, saving learners time and effort

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If the system provides detailed learning topics for every possible problem, then learners can find comprehensive learning content, but the system complexity and data requirements increase

Engineering Contradiction:

Improvelearning recommendation accuracyVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a universal problem database that can handle multiple types of problems (math, science, etc.) using a single standardized structure, allowing the system to provide reliable recommendations across different subjects without requiring separate complex systems for each domain

Inventive Principle:

Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables learners to easily find and engage with learning topics they are interested in, providing personalized recommendations that align with their learning history, thereby enhancing the learning experience.

Implementation Method 1

a camera configured to generate a formula image by photographing a region including a formula

Methodology Applied

Scientific EffectLight reflection: Reflection

Implementation Method 2

a character recognition module configured to read the formula included in the formula image by performing character recognition

Methodology Applied

Scientific EffectOptical character recognition:

Data Source

PatentUS12266198B2Apparatus and method for recommending learning using optical character recognition

Publication Date: 2025.04.01 WOONGJIN THINKBIG

AI summary

There are provided a learning recommendation apparatus and method for detecting a problem from an image through character recognition and providing at least one sub-topic learning among a plurality of sub-topic learnings related to the detected problem. The provided learning recommendation apparatus recommends, as a recommendation target, a plurality of learning topics including the concept of a formula which has been read through the character recognition for an image, wherein a priority order is set to the plurality of learning topics based on the concept distance between the learning topic and the learning history, and the learning topics are recommended so that the learning topic having a higher priority order is located at a higher position.